Dynamic Video Biometric Keys for Adaptive Data Encryption
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing encryption methods are vulnerable to data breaches and theft due to the use of static images and simple codes, which can be easily copied or stolen, lacking sufficient complexity and personalization.
Innovation Solution
Utilizing 3D image patterns and motion data from specific body parts to generate cryptographic keys, which are personalized and dynamically updated through AI to account for changes in appearance and biometric features, enhancing security by requiring multiple factors for authentication.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If simple numerical codes or static images are used for encryption, then ease of operation is improved, but security reliability deteriorates
Solution Approach 1:
The patent transforms static biometric parameters into dynamic parameters by capturing video sequences and extracting temporal features. The encryption key is generated from multiple frames showing motion patterns, breathing rates, and physiological changes over time, converting a static parameter (single image) into a dynamic parameter (temporal sequence) that cannot be easily replicated.
Solution Approach 2:
The system transitions from static image-based authentication to dynamic video-based authentication. The encryption key is continuously updated based on real-time physiological changes detected in video sequences, including heartbeat variations, respiratory patterns, and subtle facial muscle movements, making the security system adaptive and resistant to static spoofing attacks.
2Reliability
If 3D image patterns and motion data are used to generate cryptographic keys, then security reliability is improved, but device complexity increases
Solution Approach 1:
The patent extracts only the essential cryptographic key material from the video data, separating the security-critical features (temporal patterns, physiological signals) from the redundant visual information. This extraction process converts complex video sequences into compact binary key representations that can be efficiently stored and processed without requiring the full video data to be retained.
Solution Approach 2:
The system replaces complex mechanical or manual security verification processes with automated AI-based analysis of video sequences. The neural network automatically detects temporal patterns and generates encryption keys without requiring manual intervention, reducing operational complexity while enhancing security through sophisticated pattern recognition.
3Ease of manufacture
If static biometric images are used for authentication, then ease of manufacture is improved, but adaptability to user changes deteriorates
Solution Approach 1:
The system implements periodic re-authentication by requiring video sequences at scheduled intervals, ensuring that the encryption key remains synchronized with the user's current physiological state. This periodic update mechanism automatically adapts to natural changes in the user's appearance and biology without requiring manual system reconfiguration or database updates.
Data Source
AI summary
Data encryption and Human Pose Estimation based on imaging a body segment. A key for encrypting a data file is generated based on image data that represent a unique biometric feature of a body segment of a user or motion of the user. An image engine executes artificial intelligence to identify matching image data for decrypting the data file. The image engine is further trained to predict changes in image data due to aging, stress, and the like. An avatar associated with the user, which is generated based on a movement pattern of the user, is configurable for generating an encryption key and for use in an avatar-based language.